Stack Overflow
Stack Overflow

Questions tagged [tflite]

269 questions
0
votes
0 answers

Dont know the exact operation behind logsoftmax tflite operation 3d and 4d

I tried to code logsoftmax 2d its working fine..but after implementing 3d results are not matching. Can anyone please help?..I have attached the input and quantization params. int8_t data[] = { 29 ,16 ,68 ,23 ,12 ,61 ,12 ,8 ,26 ,22 ,20 ,59}; type:…
Mind_magic
  • 1
0
votes
0 answers

How to inference tflite model on multiple coral TPUs with distribution?

Is there a way to run inferencing on multiple TPUs simultaneously? I looked through the pycoral library (examples and API itself) but couldn't find anything related. I that even possible to do so with tflite?
tagiyevv
  • 11
  • 3
0
votes
0 answers

Does Hexagon Delegate for a tflite support multithreading?

I want to Hexagon Delegate to deploy a tflite model with lowest latency. I noticed the Hexagon DSP has 4 thread. So I want to enable it to see how much performance gain can achieve. I used benchmark tool to profiling the tflite using Hexagon…
Jonathan Peng
  • 1
0
votes
1 answer

Error "Check whether your GraphDef-interpreting binary is up to date with your GraphDef-generating binary." when running TFLite model in Android

I built a keras-ocr tflite model using ocr_tflite. Following are the tensorflow library versions used on mac osx m1 - tensorflow-datasets 4.8.3 tensorflow-deps 2.10.0 tensorflow-estimator 2.9.0 tensorflow-macos …
aquaman
  • 1,523
  • 5
  • 20
  • 39
0
votes
1 answer

How to resolve this "Unhandled Exception: PlatformException(Failed to run model, Interpreter busy,java.lang.RuntimeException: Interpreter busy" issue?

I am trying to create an android application utilizing the yolov5 model from TFlite. My custom detector will detect one class in real-time. As well as this app was built into my device, but after 2-3 seconds, later app closed, and an error occurred…
Md Mahadi Hasan Sany
  • 129
  • 1
  • 1
  • 12
0
votes
0 answers

AttributeError: module 'tvm.relay.op.image' has no attribute 'resize'

How to fix this problem? snpe-tflite-to-dlc --input_network MobileNetv2yolo_completeArch_305_test_loss=14.214842.ckpt-305.tflite --input_dim input "2,256,416,3" --output_path…
OliverBerry
  • 1
  • 1
0
votes
0 answers

how to read tokens from huggingface GPT2 tflite model using Interpreter

I have recently converted a pre trained gpt2 model to tflite and trying to use an interpreter for generating text from the prompt. Please find my code below which does the following: Converting the pre-trained model to tflite, works fine. Creating…
Harshil
  • 13
  • 2
0
votes
1 answer

Wrong classe names when Converting yolov5 to TFLite

when i convert my trained yolov5 custom model best.pt to best-fp16.tflite with the commande : !python yolov5/export.py --weights best.pt --include tflite .I got my converted weights with no issue However, when I ran detection with my…
Mouad Baaziz
  • 9
  • 1
0
votes
1 answer

Tensorflow Lite LSTM Model for Microprocessors on ESP32, "Type INT32 (2) not supported"

The Current error, seen when running the model on the ESP32 (An Adafruit ESP32 Huzzah): Type INT32 (2) not supported. Node ADD (number 4) failed to invoke with status 1 Node WHILE (number 2) failed to invoke with status 1 Preamble Currently…
Mehnix
  • 1
  • 3
0
votes
0 answers

GatherNd running in GPU using OpenCL?

Is there an OpenCL implementation for the GatherNd operation? I cannot find one and I'm having problem porting the logic from either CPU ot CUDA version
hamlatzis
  • 81
  • 10
0
votes
0 answers

How to extract a video frame of a participant using videosdk?

I am currently doing a medical app whereby live meetings are implemented using a third-party SDK "videosdk", and that we do classification on the patient's emotions during the live meeting. What I am trying to do here is that I want to extract a…
TryingMeBest
  • 3
  • 1
0
votes
0 answers

Was trying to convert tflite model (made using tflite model maker) to ONNX and got Unsupported TFLite OP: 36 GATHER

As the title mentions the conversion from tflite to ONNX using tflite2onnx package gives the error: Unsupported TFLite OP: 36 GATHER! The model was built using the tflite model maker with 'average_word_vec' spec for text classification. The model…
siddhartha subramaniyam
  • 83
  • 1
  • 6
0
votes
1 answer

Can't update packages via pip in google colab

I'm trying to run a python deep learning model with google colab, and I'm still after installing tflite-model-maker and tflite-support with this code  !pip install -q tflite-model-maker !pip install -q tflite-support this error: ERROR: pip's…
Jan
  • 50
  • 6
0
votes
0 answers

Fill input tensor of interpreter in tflite cpp

How to fill or provide input tensor while inferencing in cpp. i'm using memcpy like below. memcpy(interpreter->typed_input_tensor(0), frame.data, frame.step[0] * frame.rows); frame is numpy array got using opencv imread. at run time i'm…
Sagar Khimani
  • 21
  • 2
0
votes
0 answers

The plugin `tflite` uses a deprecated version (Tensorflow)

Is there a way I can resolve this tflite uses deprecated version. This is the code containing the model. import 'dart:io'; import 'package:image_picker/image_picker.dart'; import 'package:tflite/tflite.dart'; class Classifier { late File…
adlercohen
  • 1
1 2 3
…
17 18